A n a l y s i s o f C o m m o n M e t h o d s o f S t e r e o M a t c h i n g

Xinliang Zhong

Outline

· Introduction to stereo vision

· Overview of a stereo vision system

· Algorithms for stereo matching

· Applications

What is stereo vision？

 Is a technique aimed at inferring depth from

two or more cameras

 Wide research topic in computer vision

 This seminar is concerned with

• binocular stereo vision systems

• dense stereo algorithms

• stereo vision applications

Applications

Single camera

• Both (real) points (P and Q) project into the

same image point (p ≡ q)

• This occurs for each point along the same line

of sight

• Useful for optical illusions…

Stereo camera

With two (or more) cameras we can infer depth, by means of triangulation, if we are able to find corresponding

(homologous) points in the two images.

How to solve the correspondence problem

Epipolar constraint

Disparity and depth

Overview of a stereo vision system

Calibration（offline）

Rectification

Stereo Correspondence

Triangulation

Key module in stereo vision?

The algorithm is crucial in this technology

The Stereo matching problem

According to the taxonomy proposed in [1] most stereo algorithms

(subset of) these steps:

1) Matching cost computation

2) Cost aggregation

3) Disparity computation/optimization

4) Disparity refinement

Local algorithms perform:

1 => 2 =>3 (with a simple Winner Takes All (WTA) strategy)

Global Algorithms perform:

1 (=>2) =>3 (with global or semi-global reasoning)

[1] D. Scharstein and R. Szeliski, A taxonomy and evaluation of dense two-frame stereo correspondence

algorithms Int. Jour. Computer Vision, 47(1/2/3):7–42, 2002

References